Publications (8)
ActivityNarrated: An Open-Ended Narrative Paradigm for Wearable Human Activity Understanding
Lala Shakti Swarup Ray, Mengxi Liu, Alcina Pinto +4
Wearable human activity recognition (HAR) has made steady progress, yet much of this progress remains grounded in fixed-window, closed-set classification benchmarks. This formulati…
Human in the Latent Loop (HILL): Interactively Guiding Model Training Through Human Intuition
Daniel Geissler, Lars Krupp, Vishal Banwari +4
Latent space representations are critical for understanding and improving the behavior of machine learning models, yet they often remain obscure and intricate. Understanding and ex…
Beyond Confusion: A Fine-grained Dialectical Examination of Human Activity Recognition Benchmark Datasets
Daniel Geissler, Dominique Nshimyimana, Vitor Fortes Rey +3
The research of machine learning (ML) algorithms for human activity recognition (HAR) has made significant progress with publicly available datasets. However, most research priorit…
Enhancing Interpretability Through Loss-Defined Classification Objective in Structured Latent Spaces
Daniel Geissler, Bo Zhou, Mengxi Liu +1
Supervised machine learning often operates on the data-driven paradigm, wherein internal model parameters are autonomously optimized to converge predicted outputs with the ground t…
Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization
Daniel Geissler, Bo Zhou, Sungho Suh +1
A fundamental step in the development of machine learning models commonly involves the tuning of hyperparameters, often leading to multiple model training runs to work out the best…
Leveraging Hybrid Intelligence Towards Sustainable and Energy-Efficient Machine Learning
Daniel Geissler, Paul Lukowicz
Hybrid intelligence aims to enhance decision-making, problem-solving, and overall system performance by combining the strengths of both, human cognitive abilities and artificial in…